A repository for storing models that have been inter-converted between various frameworks. Supported frameworks are TensorFlow, PyTorch, ONNX, OpenVINO, TFJS, TFTRT, TensorFlowLite (Float32/16/INT8), EdgeTPU, CoreML.

PINTO_model_zoo

Please read the contents of the LICENSE file located directly under each folder before using the model. My model conversion scripts are released under the MIT license, but the license of the source model itself is subject to the license of the provider repository.

Contributors

Made with contrib.rocks.

TensorFlow Lite, OpenVINO, CoreML, TensorFlow.js, TF-TRT, MediaPipe, ONNX [.tflite, .h5, .pb, saved_model, tfjs, tftrt, mlmodel, .xml/.bin, .onnx]

I have been working on quantization of various models as a hobby, but I have skipped the work of making sample code to check the operation because it takes a lot of time. I welcome a pull request from volunteers to provide sample code. :smile:

[Note Jan 05, 2020] Currently, the MobileNetV3 backbone model and the Full Integer Quantization model do not return correctly.

[Note Jan 08, 2020] If you want the best performance with RaspberryPi4/3, install Ubuntu 19.10 aarch64 (64bit) instead of Raspbian armv7l (32bit). The official Tensorflow Lite is performance tuned for aarch64. On aarch64 OS, performance is about 4 times higher than on armv7l OS.

My article

List of pre-quantized models

* WQ = Weight Quantization ** OV = OpenVINO IR *** CM = CoreML **** DQ = Dynamic Range Quantization

1. Image Classification

No.	Model Name	Link	FP32	FP16	INT8	DQ	TPU	WQ	OV	CM	TFJS	TF-TRT	ONNX	Remarks
004	Efficientnet	■■■	⚫		⚫			⚫
010	Mobilenetv3	■■■	⚫		⚫			⚫
011	Mobilenetv2	■■■	⚫		⚫	⚫		⚫
016	Efficientnet-lite	■■■	⚫	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫
070	age-gender-recognition	■■■	⚫	⚫	⚫			⚫	⚫	⚫	⚫	⚫	⚫
083	Person_Reidentification	■■■	⚫	⚫	⚫			⚫	⚫	⚫	⚫	⚫	⚫	248,277,286,287,288,300
087	DeepSort	■■■	⚫	⚫	⚫			⚫	⚫	⚫		⚫	⚫
124	person-attributes-recognition-crossroad-0230	■■■	⚫	⚫	⚫			⚫	⚫	⚫	⚫	⚫	⚫
125	person-attributes-recognition-crossroad-0234	■■■	⚫	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫
126	person-attributes-recognition-crossroad-0238	■■■	⚫	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫
175	face-recognition-resnet100-arcface-onnx	■■■	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫	⚫	RGB/BGR,112x112,[1,512]
187	vehicle-attributes-recognition-barrier-0039	■■■	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	72x72
188	vehicle-attributes-recognition-barrier-0042	■■■	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	72x72
191	anti-spoof-mn3	■■■	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫		⚫	128x128
192	open-closed-eye-0001	■■■	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫		⚫	32x32
194	face_recognizer_fast	■■■	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	112x112
195	person_reid_youtu	■■■	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	256x128, ReID
199	NSFW	■■■	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	224x224
244	FINNger	■■■	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫		⚫	96x96
256	SFace	■■■	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫		⚫	112x112
257	PiCANet	■■■							⚫				⚫	BDDA,SAGE/224x224
259	Emotion_FERPlus	■■■	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫		⚫	64x64
290	AdaFace	■■■	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫		⚫	112x112
317	MobileOne	■■■											⚫	224x224
346	facial_expression_recognition_mobilefacenet	■■■	⚫	⚫	⚫	⚫		⚫					⚫	112x112
379	PP-LCNetV2	■■■	⚫	⚫									⚫	224x224
429	OSNet	■■■											⚫	256x128, ReID
430	FastReID	■■■											⚫	384x128, ReID
431	NITEC	■■■											⚫	224x224, Gaze Estimation
432	face-reidentification-retail-0095	■■■	⚫	⚫									⚫	128x128, FaceReID
451	DAN	■■■											⚫	224x224, Facial Expression
452	FairFace	■■■											⚫	224x224, Face Attribute
453	FairDAN	■■■											⚫	224x224, Face Attribute + Facial Expression
462	Gaze-LLE	■■■											⚫	448x448, Attention
474	Gaze-LLE-DINOv3	■■■											⚫	640x640,416x416,320x320, Attention
475	VSDLM	■■■											⚫	30x48, Lip motion
476	OCEC	■■■											⚫	24x40, Wink/Blink
477	PGC	■■■											⚫	32x32, Pointing
478	SC	■■■											⚫	32x24, Sitting
479	PUC	■■■											⚫	32x24, Phone Usage Classifier
480	HSC	■■■											⚫	48x48, Happy smile classifier
481	WHC	■■■											⚫	4x32x32,6x32x32,8x32x32, Waving Hand Classification
483	LVFace	■■■											⚫	Nx3x112x112, Cosine similarity
484	TransFace	■■■											⚫	Nx3x112x112, Cosine similarity
486	MWC	■■■											⚫	Nx3x48x48, Mask wearing classifier
489	Glasses-Detector	■■■											⚫	Glasses
491	SGC	■■■											⚫	Sunglasses
492	HHC	■■■											⚫	Hat
494	BPC	■■■											⚫	Background Plain classification
495	Comprehensive-Head-Classification	■■■	⚫										⚫	Comprehensive head classification
497	PPC	■■■											⚫	Binary classification to determine whether the subject is holding a smartphone
502	PersonViT	■■■											⚫	Person Re-Identification
503	CDNet	■■■											⚫	Person Re-Identification

2. 2D Object Detection

No.	Model Name	Link	FP32	FP16	INT8	TPU	DQ	WQ	OV	CM	TFJS	TF-TRT	ONNX	Remarks
002	Mobilenetv3-SSD	■■■	⚫		⚫			⚫		⚫
006	Mobilenetv2-SSDlite	■■■	⚫		⚫	⚫		⚫
008	Mask_RCNN_Inceptionv2	■■■	⚫	⚫				⚫
018	EfficientDet	■■■	⚫	⚫	⚫			⚫	⚫	⚫	⚫	⚫	⚫
023	Yolov3-nano	■■■	⚫	⚫				⚫					⚫
024	Yolov3-lite	■■■	⚫	⚫	⚫			⚫	⚫				⚫
031	Yolov4	■■■	⚫	⚫	⚫	⚫		⚫					⚫
034	SSD_Mobilenetv2_mnasfpn	■■■	⚫	⚫	⚫	⚫		⚫					⚫
038	SSDlite_MobileDet_edgetpu	■■■	⚫	⚫	⚫	⚫		⚫			⚫	⚫	⚫
039	SSDlite_MobileDet_cpu	■■■	⚫	⚫	⚫			⚫
042	Centernet	■■■	⚫	⚫	⚫			⚫	⚫	⚫	⚫	⚫	⚫
045	SSD_Mobilenetv2_oid_v4	■■■	⚫	⚫	⚫	⚫		⚫			⚫
046	Yolov4-tiny	■■■	⚫	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫
047	SpineNetMB_49	■■■	⚫	⚫	⚫			⚫					⚫	Mobile RetinaNet
051	East_Text_Detection	■■■	⚫	⚫	⚫	⚫		⚫	⚫		⚫	⚫	⚫
054	KNIFT	■■■	⚫	⚫	⚫			⚫	⚫				⚫	MediaPipe
056	TextBoxes++ with dense blocks, separable convolution and Focal Loss	■■■	⚫	⚫	⚫			⚫	⚫	⚫		⚫	⚫
058	keras-retinanet	■■■	⚫	⚫				⚫	⚫		⚫	⚫	⚫	resnet50_coco_best_v2.1.0.h5,320x320
072	NanoDet	■■■	⚫	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫	issue #274
073	RetinaNet	■■■	⚫	⚫	⚫			⚫	⚫	⚫	⚫	⚫	⚫
074	Yolact	■■■	⚫	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫
085	Yolact_Edge	■■■	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	21/10/05 new MobileNetV2(550x550)
089	DETR	■■■	⚫	⚫	⚫			⚫					⚫	256x256
103	EfficientDet_lite	■■■	⚫	⚫	⚫	⚫		⚫	⚫		⚫	⚫	⚫	lite0,lite1,lite2,lite3,lite4
116	DroNet	■■■	⚫	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫	DroNet,DroNetV3
123	YOLOR	■■■	⚫	⚫	⚫	⚫		⚫	⚫	⚫	⚫		⚫	ssss_s2d/320x320,640x640,960x960,1280x1280
132	YOLOX	■■■	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫		⚫	nano,tiny,s,m,l,x/256x320,320x320,416x416,480x640,544x960,736x1280,1088x1920
143	RAPiD	■■■	⚫	⚫	⚫			⚫	⚫				⚫	Fisheye, cepdof/habbof/mw_r, 608x608/1024x1024
145	text_detection_db	■■■	⚫	⚫	⚫			⚫	⚫	⚫	⚫	⚫	⚫	480x640
151	object_detection_mobile_object_localizer	■■■	⚫	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫	192x192
169	spaghettinet_edgetpu	■■■	⚫	⚫	⚫	⚫	⚫	⚫	⚫		⚫	⚫	⚫	320x320,S/M/L
174	PP-PicoDet	■■■	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫	⚫	S/M/L,320x320/416x416/640x640
178	vehicle-detection-0200	■■■	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	256x256,PriorBoxClustered->ndarray(0.npy)
179	person-detection-0202	■■■	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	512x512,PriorBoxClustered->ndarray(0.npy)
183	pedestrian-detection-adas-0002	■■■	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	384x672,PriorBox->ndarray(0.npy)
184	pedestrian-and-vehicle-detector-adas-0001	■■■	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	384x672,PriorBox->ndarray(0.npy)
185	person-vehicle-bike-detection-crossroad-0078	■■■	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫	⚫	1024x1024,PriorBoxClustered->ndarray(0.npy)
186	person-vehicle-bike-detection-crossroad-1016	■■■	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	512x512,PriorBoxClustered->ndarray(0.npy)
189	vehicle-license-plate-detection-barrier-0106	■■■	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	300x300,PriorBoxClustered->ndarray(0.npy)
190	person-detection-asl-0001	■■■	⚫	⚫	⚫		⚫	⚫	⚫				⚫	320x320
197	yolact-resnet50-fpn	■■■	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫	⚫	RGB,550x550
198	YOLOF	■■■	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫	⚫	BGR/RGB,608x608
221	YOLACT-PyTorch	■■■	⚫	⚫	⚫		⚫	⚫	⚫		⚫	⚫	⚫	180x320,240x320,320x480,480x640,544x544,720x1280
226	CascadeTableNet	■■■	⚫	⚫			⚫	⚫	⚫				⚫	General,320x320 only
262	ByteTrack	■■■											⚫	YOLOX/nano,tiny,s,m,l,x,mot17,ablation/128x320,192x320,192x448,192x640,256x320,256x448,256x640,384x640,512x1280,736x1280
264	object_localization_network	■■■											⚫	180x320,240x320,270x480,360x480,360x480,360x640,480x640,720x1280
307	YOLOv7	■■■	⚫	⚫	⚫		⚫	⚫	⚫		⚫		⚫	YOLOv7,YOLOv7-tiny
308	FastestDet	■■■	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫		⚫	180x320,256x320,320x480,352x352,352x640,480x640,736x1280
329	YOLOX-PAI	■■■											⚫
332	CrowdDet	■■■											⚫
334	DAMO-YOLO	■■■											⚫
336	PP-YOLOE-Plus	■■■											⚫
337	FreeYOLO	■■■											⚫
341	YOLOv6	■■■	⚫	⚫	⚫		⚫	⚫					⚫
356	EdgeYOLO	■■■											⚫
376	RT-DETR	■■■											⚫	ResNet50,ResNet101,HgNetv2-L,HgNetv2-X
386	naruto_handsign_detection	■■■	⚫	⚫	⚫		⚫						⚫
422	Gold-YOLO-Head-Hand	■■■											⚫	Head,Hand
424	Gold-YOLO-Body	■■■											⚫	Body
425	Gold-YOLO-Body-Head-Hand	■■■											⚫	Body,Head,Hand
426	YOLOX-Body-Head-Hand	■■■	⚫	⚫	⚫								⚫	Body,Head,Hand, tflite float16 XNNPACK boost (ARMv8.2)
434	YOLOX-Body-Head-Hand-Face	■■■											⚫	Body,Head,Hand,Face
441	YOLOX-Body-Head-Hand-Face-Dist	■■■											⚫	Body,Head,Hand,Face,Complex Distorted
442	YOLOX-Body-Head-Face-HandLR-Dist	■■■											⚫	Body,Head,Hands,Left-Hand,Right-Hand,Face,Complex Distorted
444	YOLOX-Foot-Dist	■■■											⚫	Foot,Complex Distorted
445	YOLOX-Body-Head-Face-HandLR-Foot-Dist	■■■											⚫	Body,Head,Face,Hands,Left-Hand,Right-Hand,Foot,Complex Distorted
446	YOLOX-Body-With-Wheelchair	■■■											⚫	Body with WheelChair
447	YOLOX-Wholebody-with-Wheelchair	■■■											⚫	Wholebody with WheelChair
448	YOLOX-Eye-Nose-Mouth-Ear	■■■											⚫
449	YOLOX-WholeBody12	■■■											⚫	Body,BodyWithWheelchair,Head,Face,Eye,Nose,Mouth,Ear,Hand,Hand-Left,Hand-Right,Foot
450	YOLOv9-Wholebody-with-Wheelchair	■■■											⚫	Wholebody with WheelChair
454	YOLOv9-Wholebody13	■■■											⚫	Body,BodyWithWheelchair,BodyWithCrutches,Head,Face,Eye,Nose,Mouth,Ear,Hand,Hand-Left,Hand-Right,Foot
455	YOLOv9-Gender	■■■											⚫	Body,Male,Female
456	YOLOv9-Wholebody15	■■■											⚫	Body,Male,Female,BodyWithWheelchair,BodyWithCrutches,Head,Face,Eye,Nose,Mouth,Ear,Hand,Hand-Left,Hand-Right,Foot
457	YOLOv9-Wholebody17	■■■											⚫	Body,Male,Adult,Child,Female,BodyWithWheelchair,BodyWithCrutches,Head,Face,Eye,Nose,Mouth,Ear,Hand,Hand-Left,Hand-Right,Foot
458	YOLOv9-Discrete-HeadPose-Yaw	■■■											⚫	Head,Front,Right-Front,Right-Side,Right-Back,Back,Left-Back,Left-Side,Left-Front
459	YOLOv9-Wholebody25	■■■											⚫	Body,Adult,Child,Male,Female,Body_with_Wheelchair,Body_with_Crutches,Head,Front,Right_Front,Right_Side,Right_Back,Back,Left_Back,Left_Side,Left_Front,Face,Eye,Nose,Mouth,Ear,Hand,Hand_Left,Hand_Right,Foot
460	RT-DETRv2-Wholebody25	■■■											⚫	Body,Adult,Child,Male,Female,Body_with_Wheelchair,Body_with_Crutches,Head,Front,Right_Front,Right_Side,Right_Back,Back,Left_Back,Left_Side,Left_Front,Face,Eye,Nose,Mouth,Ear,Hand,Hand_Left,Hand_Right,Foot
461	YOLOv9-Phone	■■■											⚫	Phone
463	YOLOv9-Shoulder-Elbow-Knee	■■■											⚫	Shoulder,Elbow,Knee
464	YOLOv9-Wholebody28	■■■											⚫	Body,Adult,Child,Male,Female,Body_with_Wheelchair,Body_with_Crutches,Head,Front,Right_Front,Right_Side,Right_Back,Back,Left_Back,Left_Side,Left_Front,Face,Eye,Nose,Mouth,Ear,Shoulder,Elbow,Hand,Hand_Left,Hand_Right,Knee,Foot
465	DEIM-Wholebody28	■■■											⚫	Body,Adult,Child,Male,Female,Body_with_Wheelchair,Body_with_Crutches,Head,Front,Right_Front,Right_Side,Right_Back,Back,Left_Back,Left_Side,Left_Front,Face,Eye,Nose,Mouth,Ear,Shoulder,Elbow,Hand,Hand_Left,Hand_Right,Knee,Foot
468	YOLOv9-Wholebody28-Refine	■■■											⚫	Body,Adult,Child,Male,Female,Body_with_Wheelchair,Body_with_Crutches,Head,Front,Right_Front,Right_Side,Right_Back,Back,Left_Back,Left_Side,Left_Front,Face,Eye,Nose,Mouth,Ear,Shoulder,Elbow,Hand,Hand_Left,Hand_Right,Knee,Foot
471	YOLO-Wholebody34	■■■											⚫	body,adult,child,male,female,body_with_wheelchair,body_with_crutches,head,front,right-front,right-side,right-back,back,left-back,left-side,left-front,face,eye,nose,mouth,ear,collarbone,shoulder,solar_plexus,elbow,wrist,hand,hand_left,hand_right,abdomen,hip_joint,knee,ankle,foot
472	DEIMv2-Wholebody34	■■■											⚫	body,adult,child,male,female,body_with_wheelchair,body_with_crutches,head,front,right-front,right-side,right-back,back,left-back,left-side,left-front,face,eye,nose,mouth,ear,collarbone,shoulder,solar_plexus,elbow,wrist,hand,hand_left,hand_right,abdomen,hip_joint,knee,ankle,foot
473	HISDF	■■■											⚫	Object Detection x Depth Estimation x Pose Estimation x Instance Segmentation x Binary Segmentation
482	UHD	■■■											⚫	64x64, Object Detection, Human Detection
485	DEIMv2-Wholebody40	■■■											⚫	40 classes
489	489_Glasses-Detector	■■■											⚫	glasses

3. 3D Object Detection

No.	Model Name	Link	FP32	FP16	INT8	TPU	DQ	WQ	OV	CM	TFJS	TF-TRT	ONNX	Remarks
036	Objectron	■■■	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	MediaPipe/camera,chair,chair_1stage,cup,sneakers,sneakers_1stage,ssd_mobilenetv2_oidv4_fp16
063	3D BoundingBox estimation for autonomous driving	■■■	⚫	⚫	⚫			⚫	⚫	⚫	⚫	⚫	⚫	YouTube
107	SFA3D	■■■	⚫	⚫	⚫			⚫	⚫	⚫	⚫	⚫	⚫
263	EgoNet	■■■	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫		⚫
321	DID-M3D	■■■											⚫
363	YOLO-6D-Pose	■■■	⚫								⚫		⚫	Texas Instruments ver, PINTO Special ver

4. 2D/3D Face Detection

No.	Model Name	Link	FP32	FP16	INT8	TPU	DQ	WQ	OV	CM	TFJS	TF-TRT	ONNX	Remarks
025	Head_Pose_Estimation	■■■	⚫	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫
030	BlazeFace	■■■	⚫	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫	MediaPipe
032	FaceMesh	■■■	⚫	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫	MediaPipe
040	DSFD_vgg	■■■	⚫	⚫				⚫
041	DBFace	■■■	⚫	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫	MobileNetV2/V3, 320x320,480x640,640x960,800x1280
043	Face_Landmark	■■■	⚫	⚫	⚫			⚫	⚫	⚫	⚫	⚫	⚫
049	Iris_Landmark	■■■	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	MediaPipe
095	CenterFace	■■■	⚫	⚫	⚫			⚫	⚫	⚫	⚫	⚫	⚫
096	RetinaFace	■■■	⚫	⚫	⚫			⚫	⚫	⚫	⚫	⚫	⚫
106	WHENet	■■■	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫		⚫	Real-time Fine-Grained Estimation for Wide Range Head Pose
129	SCRFD	■■■	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫	⚫	All types
134	head-pose-estimation-adas-0001	■■■	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	60x60
144	YuNet	■■■	⚫	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫	120x160
227	face-detection-adas-0001	■■■	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	384x672,PriorBox->ndarray(0.npy)
250	Face-Mask-Detection	■■■	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫		⚫	PriorBox->ndarray(0.npy)
282	face_landmark_with_attention	■■■	⚫	⚫	⚫		⚫	⚫	⚫		⚫		⚫	MediaPipe,192x192
289	face-detection-0100	■■■	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫		⚫	256x256,PriorBoxClustered->ndarray(0.npy)
293	Lightweight-Head-Pose-Estimation	■■■	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫		⚫	HeadPose, 224x224
300	6DRepNet	■■■	⚫	⚫	⚫		⚫	⚫	⚫		⚫		⚫	6D HeadPose, 224x224
301	YOLOv4_Face	■■■											⚫	480x640
302	SLPT	■■■											⚫	decoder=6/12,256x256
303	FAN	■■■	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫		⚫	Face Alignment,128x128/256x256
304	SynergyNet	■■■											⚫	6D HeadPose,224x224
305	DMHead	■■■											⚫	6D HeadPose,Multi-Model-Fused,224x224,PINTO's custom models
311	HHP-Net	■■■	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫		⚫	6D HeadPose,No-LICENSE
319	ACR-Loss	■■■	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫		⚫	Face Alignment
322	YOLOv7_Head	■■■											⚫	PINTO's custom models
383	DirectMHP	■■■	⚫	⚫									⚫
387	YuNetV2	■■■	⚫	⚫	⚫		⚫						⚫	640x640
390	BlendshapeV2	■■■	⚫	⚫									⚫	1x146x2,Nx146x2,MediaPipe
399	RetinaFace_MobileNetv2	■■■											⚫
410	FaceMeshV2	■■■	⚫	⚫	⚫		⚫		⚫				⚫	MediaPipe
414	STAR	■■■	⚫	⚫	⚫		⚫		⚫				⚫
421	Gold-YOLO-Head	■■■											⚫	Head (not Face)
423	6DRepNet360	■■■											⚫	6D HeadPose, FullRange, 224x224
433	FaceBoxes.PyTorch	■■■											⚫	2D Face
435	MobileFaceNet	■■■											⚫	Face Alignment,112x112
436	Peppa_Pig_Face_Landmark	■■■											⚫	Face Alignment,128x128,256x256
437	PIPNet	■■■											⚫	Face Alignment,256x256
443	Opal23_HeadPose	■■■											⚫	6D HeadPose, FullRange, 128x128
504	HRFFA	■■■											⚫	Face Alignment
505	YawNet	■■■											⚫	Head Pose Estimation

5. 2D/3D Hand Detection

No.	Model Name	Link	FP32	FP16	INT8	TPU	DQ	WQ	OV	CM	TFJS	TF-TRT	ONNX	Remarks
027	Minimal-Hand	■■■	⚫	⚫	⚫			⚫		⚫	⚫	⚫	⚫
033	Hand_Detection_and_Tracking	■■■	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	MediaPipe
094	hand_recrop	■■■	⚫	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫	MediaPipe
403	trt_pose_hand	■■■											⚫	2D
420	Gold-YOLO-Hand	■■■											⚫	2D
438	PeCLR	■■■											⚫	2D+3D

6. 2D/3D Human/Animal Pose Estimation

No.	Model Name	Link	FP32	FP16	INT8	TPU	DQ	WQ	OV	CM	TFJS	TF-TRT	ONNX	Remarks
003	Posenet	■■■	⚫	⚫	⚫	⚫		⚫	⚫
007	Mobilenetv2_Pose_Estimation	■■■	⚫	⚫	⚫	⚫		⚫	⚫		⚫	⚫
029	Human_Pose_Estimation_3D	■■■	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	RGB,180x320,240x320,360x640,480x640,720x1280
053	BlazePose	■■■	⚫	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫	MediaPipe
065	ThreeDPoseUnityBarracuda	■■■	⚫	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫	YouTube
080	tf_pose_estimation	■■■	⚫	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫
084	EfficientPose	■■■	⚫	⚫	⚫			⚫	⚫	⚫	⚫	⚫	⚫	SinglePose
088	Mobilenetv3_Pose_Estimation	■■■	⚫	⚫	⚫			⚫	⚫	⚫	⚫	⚫	⚫
115	MoveNet	■■■	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫	⚫	lightning,thunder
137	MoveNet_MultiPose	■■■	⚫	⚫	⚫			⚫	⚫	⚫	⚫	⚫	⚫	lightning,192x192,192x256,256x256,256x320,320x320,480x640,720x1280,1280x1920
156	MobileHumanPose	■■■	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	3D
157	3DMPPE_POSENET	■■■	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫	⚫	3D,192x192/256x256/320x320/416x416/480x640/512x512
265	PoseAug	■■■	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫		⚫	2D->3D/GCN,MLP,STGCN,VideoPose/Nx16x2
268	Lite-HRNet	■■■	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫		⚫	COCO,MPII/Top-Down
269	Higher-HRNet	■■■	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫		⚫	192x320,256x320,320x480,384x640,480x640,512x512,576x960,736x1280/Bottom-Up
271	HRNet	■■■											⚫	COCO,MPII/Top-Down
333	E2Pose	■■■	⚫	⚫	⚫		⚫						⚫	COCO/CrowdPose,End-to-End
350	P-STMO	■■■											⚫	2D->3D,in_the_wild
355	MHFormer	■■■	⚫	⚫									⚫	2D->3D
365	HTNet	■■■	⚫	⚫									⚫	2D->3D
392	STCFormer	■■■	⚫	⚫									⚫	2D->3D
393	RTMPose_WholeBody	■■■	⚫	⚫	⚫		⚫						⚫	2D
394	RTMPose_Animal	■■■	⚫	⚫	⚫		⚫						⚫	2D
402	trt_pose	■■■											⚫	2D
412	pytorch_cpn	■■■	⚫	⚫									⚫	2D
427	RTMPose_Hand	■■■											⚫	2D
440	ViTPose	■■■											⚫	2D

7. Depth Estimation from Monocular/Stereo Images

No.	Model Name	Link	FP32	FP16	INT8	TPU	DQ	WQ	OV	CM	TFJS	TF-TRT	ONNX	Remarks
009	Multi-Scale Local Planar Guidance for Monocular Depth Estimation	■■■	⚫
014	tf-monodepth2	■■■	⚫	⚫	⚫			⚫	⚫	⚫		⚫	⚫
028	struct2depth	■■■	⚫	⚫				⚫					⚫
064	Dense Depth	■■■	⚫	⚫	⚫			⚫	⚫	⚫	⚫	⚫	⚫
066	Footprints	■■■	⚫	⚫	⚫			⚫	⚫	⚫	⚫	⚫	⚫
067	MiDaS	■■■	⚫	⚫	⚫			⚫	⚫	⚫	⚫	⚫	⚫
081	MiDaS v2	■■■	⚫	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫
135	CoEx	■■■							⚫				⚫	WIP, onnx/OpenVINO only
142	HITNET	■■■	⚫	⚫				⚫					⚫	WIP issue1,issue2,flyingthings_finalpass_xl/eth3d/middlebury_d400,120x160/240x320/256x256/480x640/720x1280
146	FastDepth	■■■	⚫	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫	128x160,224x224,256x256,256x320,320x320,480x640,512x512,768x1280
147	PackNet-SfM	■■■	⚫	⚫	⚫			⚫	⚫	⚫	⚫	⚫	⚫	ddad/kitti,Convert all ResNet18 backbones only
148	LapDepth	■■■	⚫	⚫	⚫			⚫	⚫	⚫	⚫	⚫	⚫	kitti/nyu,192x320/256x320/368x640/480x640/720x1280
149	depth_estimation	■■■	⚫	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫	nyu,180x320/240x320/360x640/480x640/720x1280
150	MobileStereoNet	■■■												WIP. Conversion script only.
153	MegaDepth	■■■	⚫	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫	192x256,384x512
158	HR-Depth	■■■	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫	⚫
159	EPCDepth	■■■	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫	⚫
160	msg_chn_wacv20	■■■	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫		⚫	192x320,240x320,256x256,352x480,368x480,368x640,480x640,720x1280,1280x1920
162	PyDNet	■■■	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫	⚫
164	MADNet	■■■	⚫	⚫				⚫	⚫	⚫	⚫	⚫	⚫	Real-time-self-adaptive-deep-stereo (perform only inference mode, no-backprop, kitti)
165	RealtimeStereo	■■■	⚫	⚫			⚫	⚫	⚫		⚫	⚫	⚫	180x320,216x384,240x320,270x480,360x480,360x640,480x640,720x1280
166	Insta-DM	■■■	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫	⚫	192x320,256x320,256x832,384x640,480x640,736x1280
167	DPT	■■■	⚫	⚫			⚫	⚫	⚫	⚫	⚫	⚫	⚫	dpt-hybrid,480x640,ViT,ONNX 96x128/256x320/384x480/480x640
173	MVDepthNet	■■■							⚫				⚫	256x320
202	stereoDNN	■■■	⚫	⚫			⚫	⚫	⚫	⚫		⚫	⚫	NVSmall_321x1025,NVTiny_161x513,ResNet18_321x1025,ResNet18_2d_257x513
203	SRHNet	■■■											⚫	finetune2_kitti/sceneflow,maxdisp192,320x480/480x640
210	SC_Depth_pl	■■■	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫	⚫	kitti/nyu,320x320,320x480,480x640,640x800
211	Lac-GwcNet	■■■											⚫	kitti,240x320,320x480,480x640,720x1280
219	StereoNet	■■■	⚫	⚫	⚫		⚫	⚫	⚫			⚫	⚫	Left/180x320,240x320,320x480,360x640,480x640
235	W-Stereo-Disp	■■■											⚫	Kitti,Sceneflow/320x480,384x576,480x640
236	A-TVSNet	■■■	⚫	⚫			⚫	⚫					⚫	Stereo only/192x320,256x320,320x480,480x640
239	CasStereoNet	■■■											⚫	Stereo KITTI only/256x320,384x480,480x640,736x1280
245	GLPDepth	■■■							⚫				⚫	Kitti,NYU/192x320,320x480,384x640,480x640,736x1280,non-commercial use only
258	TinyHITNet	■■■							⚫				⚫	180x320,240x320,300x400,360x640,384x512,480x640,720x960,720x1280
266	ACVNet	■■■							⚫				⚫	sceneflow,kitti/240x320,320x480,384x640,480x640,544x960,720x1280
280	GASDA	■■■											⚫	No-LICENSE
284	CREStereo	■■■											⚫	ITER2,ITER5,ITER10,ITER20/240x320,320x480,360x640,480x640,480x640,720x1280
292	Graft-PSMNet	■■■											⚫	192x320,240x320,320x480,368x640,480x640,720x1280
294	FSRE-Depth	■■■							⚫				⚫	192x320,256x320,320x480,368x640,480x640,736x1280
296	MGNet	■■■	⚫	⚫	⚫		⚫	⚫	⚫		⚫		⚫	240x320,360x480,360x640,360x1280,480x640,720x1280
312	NeWCRFs	■■■											⚫	384x384,384x576,384x768,384x960,576x768,768x1344
313	PyDNet2	■■■	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫		⚫	Mono-Depth
327	EMDC	■■■											⚫	RGB+SarseDepth
338	Fast-ACVNet	■■■											⚫	Stereo/grid_sample opset=16,no_grid_sample opset=11
358	CGI-Stereo	■■■	⚫	⚫									⚫	Stereo
362	ZoeDepth	■■■											⚫	Mono-Depth
364	IGEV	■■■											⚫	Stereo
371	Lite-Mono	■■■											⚫	Mono
384	TCMonoDepth	■■■											⚫	Mono
397	MiDaSv3.1	■■■											⚫	Mono
415	High-frequency-Stereo-Matching-Network	■■■											⚫	Stereo
439	Depth-Anything	■■■											⚫	Mono

8. Semantic Segmentation

No.	Model Name	Link	FP32	FP16	INT8	TPU	DQ	WQ	OV	CM	TFJS	TF-TRT	ONNX	Remarks
001	deeplabv3	■■■	⚫					⚫
015	Faster-Grad-CAM	■■■	⚫		⚫			⚫
020	EdgeTPU-Deeplab	■■■	⚫	⚫	⚫			⚫
021	EdgeTPU-Deeplab-slim	■■■	⚫	⚫	⚫			⚫
026	Mobile-Deeplabv3-plus	■■■	⚫	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫
035	BodyPix	■■■	⚫	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫	MediaPipe,MobileNet0.50/0.75/1.00,ResNet50
057	BiSeNetV2	■■■	⚫	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫
060	Hair Segmentation	■■■	⚫					⚫			⚫	⚫	⚫	WIP,MediaPipe
061	U^2-Net	■■■	⚫	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫
069	ENet	■■■	⚫	⚫				⚫			⚫	⚫	⚫	Cityscapes,512x1024
075	ERFNet	■■■	⚫	⚫	⚫	⚫		⚫	⚫		⚫	⚫	⚫	Cityscapes,256x512,384x786,512x1024
078	MODNet	■■■	⚫	⚫	⚫			⚫	⚫	⚫	⚫	⚫	⚫	128x128,192x192,256x256,512x512
082	MediaPipe_Meet_Segmentation	■■■	⚫	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫	MediaPipe,128x128,144x256,96x160
104	DeeplabV3-plus	■■■	⚫	⚫	⚫			⚫	⚫	⚫	⚫		⚫	cityscapes,200x400,400x800,800x1600
109	Selfie_Segmentation	■■■	⚫	⚫	⚫			⚫	⚫	⚫	⚫	⚫	⚫	256x256
136	road-segmentation-adas-0001	■■■	⚫	⚫	⚫			⚫	⚫	⚫	⚫	⚫	⚫
138	BackgroundMattingV2	■■■	⚫	⚫				⚫	⚫				⚫	720x1280,2160x4096
181	models_edgetpu_checkpoint_and_tflite_vision_segmentation-edgetpu_tflite_default_argmax	■■■	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫
182	models_edgetpu_checkpoint_and_tflite_vision_segmentation-edgetpu_tflite_fused_argmax	■■■	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫
196	human_segmentation_pphumanseg	■■■	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫
201	CityscapesSOTA	■■■	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫		⚫	180x320,240x320,360x640,480x640,720x1280
206	Matting	■■■	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫		⚫	PaddleSeg/modnet_mobilenetv2,modnet_hrnet_w18,modnet_resnet50_vd/256x256,384x384,512x512,640x640
228	Fast-SCNN	■■■	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	192x384,384x384,384x576,576x576,576x768,768x1344
238	SUIM-Net	■■■	⚫	⚫	⚫		⚫	⚫	⚫	⚫			⚫	RSB,VGG/240x320,256x320,320x480,360x640,384x480,384x640,480x640,720x1280
242	RobustVideoMatting	■■■	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫		⚫	Mbnv3,ResNet50/192x320,240x320,320x480,384x640,480x640,720x1280,1088x1920,2160x3840
246	SqueezeSegV3	■■■	⚫	⚫			⚫	⚫	⚫	⚫	⚫		⚫	21,53/180x320,240x320,320x480,360x640,480x640,720x1280
267	LIOT	■■■	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫		⚫	180x320,240x320,320x480,360x640,480x640,540x960,720x1280,1080x1920
287	Topformer	■■■	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫		⚫	Tiny,Small,Base/448x448,512x512
295	SparseInst	■■■							⚫				⚫	r50_giam_aug/192x384,384x384,384x576,384x768,576x576,576x768,768x1344
299	DGNet	■■■	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫		⚫
313	IS-Net	■■■											⚫	180x320,240x320,320x480,360x640,480x640,720x1280,1080x1920,1080x2048,2160x4096,N-batch,Dynamic-HeightxWidth
335	PIDNet	■■■											⚫	Cityscapes,CamVid/Dynamic-HeightxWidth
343	PP-MattingV2	■■■	⚫	⚫									⚫	HumanSeg
347	RGBX_Semantic_Segmentation	■■■											⚫
369	Segment_Anything	■■■											⚫
380	Skin-Clothes-Hair-Segmentation-using-SMP	■■■	⚫	⚫									⚫
391	MagicTouch	■■■	⚫	⚫			⚫						⚫	MediaPipe
405	Ear_Segmentation	■■■											⚫	Ear
417	PopNet	■■■											⚫	Saliency
466	People_Segmentation	■■■											⚫	UNet
467	Human_Parsing	■■■											⚫
470	RHIS	■■■											⚫	UNet+UNet
489	489_Glasses-Detector	■■■											⚫	glasses

9. Anomaly Detection

No.	Model Name	Link	FP32	FP16	INT8	TPU	WQ	OV	CM	TFJS	TF-TRT	ONNX	Remarks
005	One_Class_Anomaly_Detection	■■■	⚫		⚫	⚫	⚫
099	Efficientnet_Anomaly_Detection_Segmentation	■■■	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫

10. Artistic

No.	Model Name	Link	FP32	FP16	INT8	TPU	DQ	WQ	OV	CM	TFJS	TF-TRT	ONNX	Remarks
017	Artistic-Style-Transfer	■■■	⚫	⚫	⚫			⚫	⚫	⚫	⚫		⚫
019	White-box-Cartoonization	■■■	⚫	⚫	⚫			⚫	⚫	⚫	⚫	⚫	⚫
037	First_Neural_Style_Transfer	■■■	⚫					⚫					⚫
044	Selfie2Anime	■■■	⚫	⚫	⚫			⚫	⚫	⚫			⚫
050	AnimeGANv2	■■■	⚫	⚫	⚫			⚫	⚫	⚫		⚫	⚫
062	Facial Cartoonization	■■■	⚫	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫
068	Colorful_Image_Colorization	■■■	⚫	⚫				⚫	⚫	⚫	⚫		⚫	experimental
101	arbitrary_image_stylization	■■■	⚫	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫	magenta
113	Anime2Sketch	■■■	⚫	⚫	⚫			⚫	⚫	⚫	⚫	⚫	⚫
161	EigenGAN-Tensorflow	■■■	⚫	⚫	⚫			⚫	⚫	⚫	⚫	⚫	⚫	Anime,CelebA
193	CoCosNet	■■■	⚫	⚫			⚫	⚫	⚫	⚫	⚫		⚫	RGB,256x256

11. Super Resolution

No.	Model Name	Link	FP32	FP16	INT8	TPU	DQ	WQ	OV	CM	TFJS	TF-TRT	ONNX	Remarks
012	Fast_Accurate_and_Lightweight_Super-Resolution	■■■	⚫		⚫			⚫
022	Learning_to_See_Moving_Objects_in_the_Dark	■■■	⚫	⚫				⚫					⚫
071	Noise2Noise	■■■	⚫	⚫	⚫	⚫		⚫					⚫	srresnet/clear only
076	Deep_White_Balance	■■■	⚫	⚫				⚫	⚫	⚫	⚫	⚫	⚫
077	ESRGAN	■■■	⚫	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫	50x50->x4, 100x100->x4
079	MIRNet	■■■	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	Low-light Image Enhancement/40x40,80x80,120x120,120x160,120x320,120x480,120x640,120x1280,180x480,180x640,180x1280,180x320,240x320,240x480,360x480,360x640,480x640,720x1280
086	Defocus Deblurring Using Dual-Pixel	■■■	⚫	⚫	⚫			⚫	⚫	⚫	⚫	⚫	⚫
090	Ghost-free_Shadow_Removal	■■■	⚫	⚫	⚫			⚫	⚫	⚫			⚫	256x256
111	SRN-Deblur	■■■	⚫	⚫	⚫			⚫	⚫	⚫	⚫	⚫	⚫	240x320,480x640,720x1280,1024x1280
112	DeblurGANv2	■■■	⚫	⚫	⚫			⚫	⚫	⚫	⚫	⚫	⚫	inception/mobilenetv2:256x256,320x320,480x640,736x1280,1024x1280
114	Two-branch-dehazing	■■■	⚫	⚫	⚫			⚫	⚫		⚫	⚫	⚫	240x320,480x640,720x1280
133	Real-ESRGAN	■■■	⚫	⚫				⚫	⚫	⚫	⚫	⚫	⚫	16x16,32x32,64x64,128x128,240x320,256x256,320x320,480x640
152	DeepLPF	■■■	⚫	⚫				⚫	⚫				⚫
170	Learning-to-See-in-the-Dark	■■■	⚫	⚫	⚫			⚫	⚫	⚫	⚫	⚫	⚫	sony/fuji, 240x320,360x480,360x640,480x640
171	Fast-SRGAN	■■■	⚫	⚫	⚫	⚫		⚫	⚫	⚫			⚫	120x160,128x128,240x320,256x256,480x640,512x512
172	Real-Time-Super-Resolution	■■■	⚫	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫	64x64,96x96,128x128,256x256,240x320,480x640
176	StableLLVE	■■■	⚫	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫	Low-light Image/Video Enhancement,180x240,240x320,360x640,480x640,720x1280
200	AGLLNet	■■■	⚫	⚫				⚫	⚫	⚫	⚫	⚫	⚫	Low-light Image/Video Enhancement,256x256,256x384,384x512,512x640,768x768,768x1280
204	HINet	■■■	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫	⚫	DeBlur,DeNoise,DeRain/256x320,320x480,480x640
205	MBLLEN	■■■	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	Low-light Image/Video Enhancement,180x320,240x320,360x640,480x640,720x1280
207	GLADNet	■■■	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	Low-light Image/Video Enhancement,180x320,240x320,360x640,480x640,720x1280,No-LICENSE
208	SAPNet	■■■	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫		⚫	DeRain,180x320,240x320,360x640,480x640,720x1280
209	MSBDN-DFF	■■■	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫		⚫	Dehazing,192x320,240x320,320x480,384x640,480x640,720x1280,No-LICENSE
212	GFN	■■■	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	DeBlur+SuperResolution,x4/64x64,96x96,128x128,192x192,240x320,256x256,480x640,720x1280
213	TBEFN	■■■	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	Low-light Image Enhancement/180x320,240x320,320x480,360x640,480x640,720x1280
214	EnlightenGAN	■■■	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫	⚫	Low-light Image Enhancement/192x320,240x320,320x480,368x640,480x640,720x1280
215	AOD-Net	■■■	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	DeHazing/180x320,240x320,320x480,360x640,480x640,720x1280
216	Zero-DCE-TF	■■■	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	Low-light Image Enhancement/180x320,240x320,320x480,360x640,480x640,720x1280
217	RUAS	■■■	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	Low-light Image Enhancement/180x320,240x320,320x480,360x640,480x640,720x1280,No-LICENSE
218	DSLR	■■■	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫		⚫	Low-light Image Enhancement/256x256,256x384,256x512,384x640,512x640,768x1280
220	HEP	■■■	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫	⚫	Low-light Image Enhancement/180x320,240x320,320x480,360x640,480x640
222	LFT	■■■											⚫	Transformer/2x,4x/65x65
223	DA_dahazing	■■■	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫		⚫	DeHazing/192x320,240x320,320x480,360x640,480x640,720x1280,No-LICENSE
224	Y-net	■■■	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫		⚫	DeHazing/192x320,240x320,320x480,384x640,480x640,720x1280
225	DRBL	■■■	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫		⚫	DeHazing/192x320,240x320,320x480,384x640,480x640,720x1280
230	Single-Image-Desnowing-HDCWNet	■■■	⚫	⚫			⚫	⚫			⚫		⚫	DeSnowing/512x672
231	DRBL	■■■	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫	⚫	Low-light Image Enhancement/180x320,240x320,320x480,360x640,480x640,720x1280,No-LICENSE
232	MIMO-UNet	■■■	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫	⚫	DeBlur/180x320,240x320,320x480,360x640,480x640,720x1280,No-LICENSE
234	FBCNN	■■■	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫		⚫	DeNoise/180x320,240x320,320x480,360x640,480x640,720x1280
240	BSRGAN	■■■	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫		⚫	x2,x4/64x64,96x96,128x128,160x160,180x320,240x320,No-LICENSE
241	SCL-LLE	■■■	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	Low-light Image Enhancement/180x320,240x320,320x480,480x640,720x1280,No-LICENSE
243	Zero-DCE-improved	■■■	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫		⚫	Low-light Image Enhancement/180x320,240x320,320x480,360x640,480x640,720x1280,academic use only
249	Real-CUGAN	■■■								⚫			⚫	2x,3x,4x/64x64,96x96,128x128,120x160,160x160,180x320,240x320
251	AU-GAN	■■■	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫		⚫	Low-light Image Enhancement/128x256,240x320,240x640,256x512,480x640,512x1024,720x1280
253	TransWeather	■■■							⚫				⚫	DeRain,DeHaizing,DeSnow/192x320,256x320,320x480,384x640,480x640,736x1280
261	EfficientDerain	■■■											⚫	v4_SPA,v4_rain100H,v4_rain1400/192x320,256x320,320x480,384x640,480x640,608x800,736x1280
270	HWMNet	■■■											⚫	Low-light Image Enhancement/192x320,256x320,320x480,384x640,480x640,544x960,720x1280
275	FD-GAN	■■■	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫		⚫	DeHaizing/192x320,256x320,384x640,480x640,720x1280,1080x1920,No-LICENSE
277	EDN-GTM	■■■	⚫	⚫			⚫	⚫	⚫	⚫	⚫		⚫	DeHaizing/192x320,240x320,384x480,480x640,512x512,720x1280,1088x1920
281	IMDN	■■■	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫		⚫	x4/64x64,96x96,128x128,120x160,160x160,180x320,192x192,256x256,180x320,240x320,360x640,480x640
283	UIE-WD	■■■											⚫	Underwater Image Enhancement/WIP issue #97/192x320,240x320,320x480,360x640,480x640,720x1280,1080x1920
285	Decoupled-Low-light-Image-Enhancement	■■■											⚫	Low-light Image Enhancement/180x320,240x320,360x480,360x640,480x640,720x1280
286	SCI	■■■	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫	⚫	Low-light Image Enhancement/180x320,240x320,360x480,360x640,480x640,720x1280
315	Illumination-Adaptive-Transformer	■■■											⚫	Low-light Image Enhancement
316	night_enhancement	■■■											⚫	Low-light Image Enhancement
320	Dehamer	■■■											⚫	Dehazing
323	Stripformer	■■■											⚫	DeBlur
325	DehazeFormer	■■■											⚫	Dehazing
344	XYDeblur	■■■											⚫	DeBlur
348	Bread	■■■											⚫	Low-light Image Enhancement
348	PMN	■■■											⚫	DeNoise, Low-light Image Enhancement
351	RFDN	■■■											⚫	x4
352	MAXIM	■■■	⚫	⚫									⚫	Dehaze only
353	ShadowFormer	■■■											⚫	Shadow Removal
354	DEA-Net	■■■	⚫	⚫									⚫	DeHaze
359	MSPFN	■■■	⚫	⚫									⚫	DeRain
361	KBNet	■■■											⚫	Real Image Denoising
367	FLW-Net	■■■											⚫	Low-light Image Enhancement
368	C2PNet	■■■											⚫	DeHaze
370	Semantic-Guided-Low-Light-Image-Enhancement	■■■											⚫	Low-light Image Enhancement
372	URetinex-Net	■■■											⚫	Low-light Image Enhancement
375	SCANet	■■■											⚫	DeHaze
377	DRSformer	■■■											⚫	DeRain
385	PairLIE	■■■											⚫	Low-light Image Enhancement
389	WGWS-Net	■■■											⚫	DeRain,DeRainDrop,DeHaize,DeSnow
396	MixDehazeNet	■■■											⚫	DeHaize
400	CSRNet	■■■											⚫	Low-light Image Enhancement
404	HDR-Transformer	■■■											⚫
409	nighttime_dehaze	■■■											⚫	DeHaze
411	UDR-S2Former_deraining	■■■											⚫	DeRain
418	Diffusion-Low-Light	■■■	⚫	⚫									⚫	Diffusion, Low-light Image Enhancement
469	Face_Deblurring	■■■											⚫	64x64, HxW

12. Sound Classifier

No.	Model Name	Link	FP32	FP16	INT8	TPU	DQ	WQ	OV	CM	TFJS	TF-TRT	ONNX	Remarks
013	ml-sound-classifier	■■■	⚫	⚫	⚫			⚫	⚫		⚫	⚫
097	YAMNet	■■■	⚫	⚫	⚫			⚫	⚫	⚫	⚫	⚫	⚫
098	SPICE	■■■	⚫	⚫	⚫			⚫			⚫	⚫
118	Speech-enhancement	■■■	⚫	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫	WIP,EdgeTPU(LeakyLeRU)
120	FRILL	■■■	⚫	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫	nofrontend
177	BirdNET-Lite	■■■	⚫	⚫	⚫		⚫	⚫				⚫		non-flex
381	Whisper	■■■										⚫
382	Light-SERNet	■■■	⚫	⚫	⚫

13. Natural Language Processing

No.	Model Name	Link	FP32	FP16	WQ	OV	CM	TFJS	TF-TRT	ONNX
048	Mobile_BERT	■■■	⚫	⚫	⚫	⚫	⚫	⚫		⚫
121	GPT2/DistillGPT2	■■■	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫
122	DistillBert	■■■	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫

14. Text Recognition

No.	Model Name	Link	FP32	FP16	INT8	WQ	OV	CM	TFJS	TF-TRT	ONNX	Remarks
052	Handwritten_Text_Recognition	■■■	⚫	⚫		⚫
055	Handwritten_Japanese_Recognition	■■■	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫
093	ocr_japanese	■■■	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	120x160

15. Action Recognition

No.	Model Name	Link	FP32	FP16	INT8	TPU	WQ	OV	CM	TF-TRT	ONNX	Remarks
092	weld-porosity-detection-0001	■■■	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫
247	PoseC3D	■■■									⚫	Skeleton-based/FineGYM,NTU60_XSub,NTU120_XSub,UCF101,HMDB51/1x20x48x64x64
248	MS-G3D	■■■									⚫	Skeleton-based/Kinetics,NTU60,NTU120/1x3xTx25x2

16. Inpainting

No.	Model Name	Link	FP32	FP16	INT8	DQ	WQ	OV	CM	TFJS	ONNX
100	HiFill	■■■	⚫	⚫			⚫	⚫			⚫
163	MST_inpainting	■■■	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫	⚫
273	OPN(Onion-Peel Networks)	■■■									⚫
274	DeepFillv2	■■■	⚫	⚫		⚫	⚫	⚫			⚫

17. GAN

No.	Model Name	Link	FP32	FP16	INT8	TPU	WQ	OV	CM	TFJS	TF-TRT	ONNX	Remarks
105	MobileStyleGAN	■■■	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫
310	attentive-gan-derainnet	■■■	⚫	⚫	⚫		⚫	⚫	⚫	⚫		⚫	DeRain/180x320,240x320,240x360,320x480,360x640,480x640,720x1280

18. Transformer

No.	Model Name	Link	FP32	FP16	INT8	TPU	WQ	OV	CM	TFJS	TF-TRT	ONNX	Remarks
127	dino	■■■	⚫	⚫			⚫	⚫	⚫	⚫		⚫	experimental,dino_deits8/dino_deits16

19. Others

No.	Model Name	Link	FP32	FP16	INT8	TPU	DQ	WQ	OV	CM	TFJS	TF-TRT	ONNX	Remarks
091	gaze-estimation-adas-0002	■■■	⚫	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫
102	Coconet	■■■	⚫	⚫				⚫			⚫			magenta
108	HAWP	■■■											⚫	Line Parsing,WIP
110	L-CNN	■■■											⚫	Line Parsing,WIP
117	DTLN	■■■	⚫	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫
119	M-LSD	■■■	⚫	⚫	⚫			⚫	⚫	⚫	⚫	⚫	⚫
131	CFNet	■■■											⚫	256x256,512x768
139	PSD-Principled-Synthetic-to-Real-Dehazing-Guided-by-Physical-Priors	■■■	⚫	⚫				⚫	⚫	⚫	⚫	⚫	⚫
140	Ultra-Fast-Lane-Detection	■■■	⚫	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫	288x800
141	lanenet-lane-detection	■■■	⚫	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫	256x512
154	driver-action-recognition-adas-0002-encoder	■■■	⚫	⚫			⚫	⚫	⚫	⚫	⚫	⚫	⚫
155	driver-action-recognition-adas-0002-decoder	■■■	⚫	⚫			⚫	⚫	⚫	⚫	⚫	⚫	⚫
167	LSTR	■■■	⚫	⚫			⚫	⚫	⚫		⚫		⚫	180x320,240x320,360x640,480x640,720x1280
229	DexiNed	■■■	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫	⚫	⚫	160x320,320x480,368x640,480x640,720x1280
233	HRNet-for-Fashion-Landmark-Estimation	■■■	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫		⚫	192x320,256x320,320x480,384x640,480x640,736x1280
237	piano_transcription	■■■							⚫				⚫	1x160000,Nx160000
252	RAFT	■■■											⚫	small,chairs,kitti,sintel,things/iters=10,20/240x320,360x480,480x640
254	FullSubNet-plus	■■■											⚫	1x1x257x100,200,500,1000,2000,3000,5000,7000,8000,10000
255	FILM	■■■	⚫	⚫			⚫	⚫	⚫		⚫		⚫	L1,Style,VGG/256x256,180x320,240x320,360x640,480x640,720x1280,1080x1920
260	KP2D	■■■	⚫	⚫			⚫	⚫	⚫				⚫	ResNet/128x320,192x320,192x448,192x640,256x320,256x448,256x640,320x448,384x640,480x640,512x1280,736x1280
272	CSFlow	■■■											⚫	chairs,kitti,things/iters=10,20/192x320,240x320,320x480,384x640,480x640,736x1280
276	HybridNets	■■■	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫		⚫	anchor_HxW.npy/256x384,256x512,384x512,384x640,384x1024,512x640,768x1280,1152x1920
278	DWARF	■■■	⚫	⚫	⚫		⚫	⚫	⚫	⚫	⚫		⚫	StereoDepth+OpticalFlow,/192x320,256x320,384x640,512x640,512x640,768x1280
279	F-Clip	■■■	⚫	⚫	⚫		⚫	⚫	⚫		⚫		⚫	Line Parsing/ALL/192x320,256x320,320x480,384x640,480x640,736x1280
288	perceptual-reflection-removal	■■■	⚫	⚫	⚫		⚫	⚫	⚫		⚫		⚫	Reflection-Removal/180x320,240x320,360x480,360x640,480x640,720x1280
291	SeAFusion	■■■	⚫	⚫			⚫	⚫	⚫		⚫		⚫	180x320,240x320,360x480,360x640,480x640,720x1280
297	GazeNet	■■■											⚫	1x7x3x256x192/NxFx3x256x192
298	DEQ-Flow	■■■											⚫	AGPL-3.0 license
306	GMFlowNet	■■■											⚫	OpticalFlow/192x320,240x320,320x480,360x640,480x640,720x1280
309	ImageForensicsOSN	■■■	⚫	⚫	⚫		⚫	⚫	⚫		⚫		⚫	forgery detection/180x320,240x320,320x480,360x640,480x640,720x1280
318	pips	■■■											⚫
324	Ultra-Fast-Lane-Detection-v2	■■■											⚫
326	YOLOPv2	■■■	⚫	⚫			⚫	⚫	⚫				⚫
328	Stable_Diffusion	■■■											⚫
339	DeepLSD	■■■											⚫
342	ALIKE	■■■	⚫	⚫	⚫		⚫	⚫					⚫
357	Unimatch	■■■	⚫	⚫									⚫	OpticalFlow, StereoDepth
360	PARSeq	■■■	⚫	⚫									⚫	Scene Text Recognition
366	text_recognition_CRNN	■■■	⚫	⚫									⚫	CN/CH/EN
373	LiteTrack	■■■	⚫	⚫									⚫	Tracking
374	LaneSOD	■■■											⚫	Lane Segmentation
378	P2PNet_tfkeras	■■■	⚫	⚫									⚫
388	LightGlue	■■■											⚫	Keypoint Matching
398	L2CS-Net	■■■	⚫	⚫	⚫		⚫						⚫	Gaze Pose 448x448
401	CLRerNet	■■■											⚫	Lane Detection
406	DeDoDe	■■■	⚫	⚫									⚫	Keypoint Detection, Description, Matching
407	Generalizing_Gaze_Estimation	■■■	⚫	⚫									⚫	Gaze Pose 160x160
408	UAED	■■■											⚫	Edge Detectopm
413	DocShadow	■■■	⚫										⚫	Document Shadow Removal
416	GeoNet	■■■	⚫										⚫	MonoDepth, CameraPose, OpticalFlow
428	ISR	■■■											⚫	Person ReID
487	DDN	■■■											⚫	edge detector
490	ICAONet	■■■	⚫	⚫						⚫			⚫	ISO/IEC 19794-5
492	Efficient-FIQA	■■■	⚫	⚫							⚫		⚫	Efficient Face Image Quality Assessment
496	LGT-Net	■■■											⚫	Indoor Panoramic Room Layout Estimation
498	DocRes	■■■											⚫	A Generalist Model Toward Unifying Document Image Restoration Tasks
499	LINEA	■■■											⚫	Fast and accurate line detection using scalable transformers
500	ScaleLSD	■■■											⚫	Scalable Deep Line Segment Detection Streamlined
501	LINEAE	■■■											⚫	Line Segment Detection

Sample.1 - Object detection by video file

RaspberryPi4 (CPU only)
Raspbian Buster 64bit
Tensorflow / Tensorflow Lite with multi-thread acceleration tuning for PythonAPI
MobileNetV2-SSDLite 300x300 Integer Quantization
Pascal-VOC Dataset (Japanese article)
MP4 30FPS, 640x360
Approximately 14FPS ~ 15FPS for all processes from pre-processing, inference, post-processing, and display

$ cd 006_mobilenetv2-ssdlite/02_voc/03_integer_quantization
$ ./download.sh && cd ..
$ python3 mobilenetv2ssdlite_movie_sync.py

004

Sample.2 - Object detection by USB Camera

RaspberryPi4 (CPU only)
Ubuntu 19.10 64bit
Tensorflow / Tensorflow Lite with multi-thread acceleration tuning for PythonAPI
MobileNetV2-SSDLite 300x300 Integer Quantization
Pascal-VOC Dataset (Japanese article)
USB Camera, 640x480
IPS 1080p HDMI Display
Approximately 12FPS for all processes from pre-processing, inference, post-processing, and display

$ cd 006_mobilenetv2-ssdlite/02_voc/03_integer_quantization
$ ./download.sh && cd ..
$ python3 mobilenetv2ssdlite_usbcam_sync.py

005

Sample.3 - Head Pose Estimation, Multi-stage inference with multi-model

RaspberryPi4 (CPU only)
Ubuntu 19.10 64bit
Tensorflow / Tensorflow Lite with multi-thread acceleration tuning for PythonAPI
[Model.1] MobileNetV2-SSDLite dm=0.5 300x300, Integer Quantization
[Model.2] Head Pose Estimation 128x128, Integer Quantization
WIDERFACE
USB Camera, 640x480
IPS 1080p HDMI Display
Approximately 13FPS for all processes from pre-processing, inference, post-processing, and display

$ cd 025_head_pose_estimation/03_integer_quantization
$ ./download.sh
$ python3 head_pose_estimation.py

006

Sample.4 - Semantic Segmentation, DeeplabV3-plus 256x256

RaspberryPi4 (CPU only)
Ubuntu 19.10 64bit
Tensorflow / Tensorflow Lite with multi-thread acceleration tuning for PythonAPI
DeeplabV3-plus (MobileNetV2) Decoder 256x256, Integer Quantization
USB Camera, 640x480
IPS 1080p HDMI Display
Approximately 8.5 FPS for all processes from pre-processing, inference, post-processing, and display

$ cd 026_mobile-deeplabv3-plus/03_integer_quantization
$ ./download.sh
$ python3 deeplabv3plus_usbcam.py

007

Sample.5 - MediaPipe/FaceMesh, face_detection_front_128_weight_quant, face_landmark_192_weight_quant

Ubuntu 18.04 x86_64
Tensorflow Lite
C/C++
OpenGL
USB Camera, 640x480
$ v4l2-ctl --set-fmt-video=width=640,height=480,pixelformat=YUYV
Test Code - tflite_gles_app - gl2facemesh - @terryky

Sample.6 - MediaPipe/Objectron, object_detection_3d_chair_640x480_weight_quant

Ubuntu 18.04 x86_64
Tensorflow Lite
C/C++
OpenGL
USB Camera, 640x480
$ v4l2-ctl --set-fmt-video=width=640,height=480,pixelformat=YUYV
Test Code - tflite_gles_app - gl2objectron - @terryky

Sample.7 - MediaPipe/Objectron, object_detection_3d_chair_640x480_openvino_FP32

Ubuntu 18.04 x86_64
OpenVINO 2020.2
Python
Core i7 (CPU only)
USB Camera, 640x480
Test Code - objectron-3d-object-detection-openvino - @yas-sim

Sample.8 - MediaPipe/BlazeFace, face_detection_front_128_integer_quant

RaspberryPi4
Ubuntu 19.10 aarch64
Tensorflow Lite
C/C++
OpenGL
USB Camera, 640x480
$ v4l2-ctl --set-fmt-video=width=640,height=480,pixelformat=YUYV
Test Code - tflite_gles_app - gl2blazeface - @terryky

Sample.9 - MediaPipe/Hand_Detection_and_Tracking(3D Hand Pose), hand_landmark_3d_256_integer_quant.tflite + palm_detection_builtin_256_integer_quant.tflite

RaspberryPi4
Tensorflow Lite
C/C++
OpenGL
Test Code - tflite_gles_app - gl2handpose - @terryky

Sample.10 - DBFace, 640x480_openvino_FP32

Ubuntu 18.04 x86_64
OpenVINO 2020.2
Python
Core i7 (CPU only)
USB Camera, 640x480
Test Code - DBFace-on-OpenVINO - @yas-sim

Sample.11 - Human_Pose_Estimation_3D, 640x480, Tensorflow.js + WebGL + Browser

Ubuntu 18.04 x86_64
Tensorflow.js
USB Camera, 640x480
Test Code - tfjs_webgl_app - @terryky

Sample.12 - BlazePose Full Body, 640x480, Tensorflow.js + WebGL + Browser

Ubuntu 18.04 x86_64
Tensorflow.js
USB Camera, 640x480
Test Code - tfjs_webgl_app - @terryky

Sample.13 - Facial Cartoonization, 640x480, OpenVINO Corei7 CPU only

Ubuntu 18.04 x86_64
OpenVINO
USB Camera, 640x480
Test Code

1. Environment

Ubuntu 18.04 x86_64
RaspberryPi4 Raspbian Buster 32bit / Raspbian Buster 64bit / Ubuntu 19.10 aarch64
Tensorflow-GPU v1.15.2 or Tensorflow v2.3.1+
OpenVINO 2020.2+
PyTorch 1.6.0+
ONNX Opset12
Python 3.6.8
PascalVOC Dataset
COCO Dataset
Cityscapes Dataset
Imagenette Dataset
CelebA Dataset
Audio file (.wav)
WIDERFACE
Google Colaboratory

2. Procedure

Procedure examples

2-1. MobileNetV3+DeeplabV3+PascalVOC

2-1-1. Preparation

$ cd ~
$ mkdir deeplab;cd deeplab
$ git clone --depth 1 https://github.com/tensorflow/models.git
$ cd models/research/deeplab/datasets
$ mkdir pascal_voc_seg

$ curl -sc /tmp/cookie \
  "https://drive.google.com/uc?export=download&id=1rATNHizJdVHnaJtt-hW9MOgjxoaajzdh" > /dev/null
$ CODE="$(awk '/_warning_/ {print $NF}' /tmp/cookie)"
$ curl -Lb /tmp/cookie \
  "https://drive.google.com/uc?export=download&confirm=${CODE}&id=1rATNHizJdVHnaJtt-hW9MOgjxoaajzdh" \
  -o pascal_voc_seg/VOCtrainval_11-May-2012.tar

$ sed -i -e "s/python .\/remove_gt_colormap.py/python3 .\/remove_gt_colormap.py/g" \
      -i -e "s/python .\/build_voc2012_data.py/python3 .\/build_voc2012_data.py/g" \
      download_and_convert_voc2012.sh

$ sh download_and_convert_voc2012.sh

$ cd ../..
$ mkdir -p deeplab/datasets/pascal_voc_seg/exp/train_on_train_set/train
$ mkdir -p deeplab/datasets/pascal_voc_seg/exp/train_on_train_set/eval
$ mkdir -p deeplab/datasets/pascal_voc_seg/exp/train_on_train_set/vis

$ export PATH_TO_TRAIN_DIR=${HOME}/deeplab/models/research/deeplab/datasets/pascal_voc_seg/exp/train_on_train_set/train
$ export PATH_TO_DATASET=${HOME}/deeplab/models/research/deeplab/datasets/pascal_voc_seg/tfrecord
$ export PYTHONPATH=${HOME}/deeplab/models/research:${HOME}/deeplab/models/research/deeplab:${HOME}/deeplab/models/research/slim:${PYTHONPATH}

# See feature_extractor.network_map for supported model variants.
# models/research/deeplab/core/feature_extractor.py

networks_map = {
    'mobilenet_v2': _mobilenet_v2,
    'mobilenet_v3_large_seg': mobilenet_v3_large_seg,
    'mobilenet_v3_small_seg': mobilenet_v3_small_seg,
    'resnet_v1_18': resnet_v1_beta.resnet_v1_18,
    'resnet_v1_18_beta': resnet_v1_beta.resnet_v1_18_beta,
    'resnet_v1_50': resnet_v1_beta.resnet_v1_50,
    'resnet_v1_50_beta': resnet_v1_beta.resnet_v1_50_beta,
    'resnet_v1_101': resnet_v1_beta.resnet_v1_101,
    'resnet_v1_101_beta': resnet_v1_beta.resnet_v1_101_beta,
    'xception_41': xception.xception_41,
    'xception_65': xception.xception_65,
    'xception_71': xception.xception_71,
    'nas_pnasnet': nas_network.pnasnet,
    'nas_hnasnet': nas_network.hnasnet,
}

2-1-2. "mobilenet_v3_small_seg" Float32 regular training

$ python3 deeplab/train.py \
    --logtostderr \
    --training_number_of_steps=500000 \
    --train_split="train" \
    --model_variant="mobilenet_v3_small_seg" \
    --decoder_output_stride=16 \
    --train_crop_size="513,513" \
    --train_batch_size=8 \
    --dataset="pascal_voc_seg" \
    --save_interval_secs=300 \
    --save_summaries_secs=300 \
    --save_summaries_images=True \
    --log_steps=100 \
    --train_logdir=${PATH_TO_TRAIN_DIR} \
    --dataset_dir=${PATH_TO_DATASET}

2-1-3. "mobilenet_v3_large_seg" Float32 regular training

$ python3 deeplab/train.py \
    --logtostderr \
    --training_number_of_steps=1000000 \
    --train_split="train" \
    --model_variant="mobilenet_v3_large_seg" \
    --decoder_output_stride=16 \
    --train_crop_size="513,513" \
    --train_batch_size=8 \
    --dataset="pascal_voc_seg" \
    --save_interval_secs=300 \
    --save_summaries_secs=300 \
    --save_summaries_images=True \
    --log_steps=100 \
    --train_logdir=${PATH_TO_TRAIN_DIR} \
    --dataset_dir=${PATH_TO_DATASET}

2-1-4. Visualize training status

$ tensorboard \
  --logdir ${HOME}/deeplab/models/research/deeplab/datasets/pascal_voc_seg/exp/train_on_train_set/train

2-2. MobileNetV3+DeeplabV3+Cityscaps - Post-training quantization

2-2-1. Preparation

$ cd ~
$ mkdir -p git/deeplab && cd git/deeplab
$ git clone --depth 1 https://github.com/tensorflow/models.git
$ cd models/research/deeplab/datasets
$ mkdir cityscapes && cd cityscapes

# Clone the script to generate Cityscapes Dataset.
$ git clone --depth 1 https://github.com/mcordts/cityscapesScripts.git
$ mv cityscapesScripts cityscapesScripts_ && \
  mv cityscapesScripts_/cityscapesscripts . && \
  rm -rf cityscapesScripts_

# Download Cityscapes Dataset.
# https://www.cityscapes-dataset.com/
# You will need to sign up and issue a userID and password to download the data set.
$ wget --keep-session-cookies --save-cookies=cookies.txt \
  --post-data 'username=(userid)&password=(password)&submit=Login' \
  https://www.cityscapes-dataset.com/login/
$ wget --load-cookies cookies.txt \
  --content-disposition https://www.cityscapes-dataset.com/file-handling/?packageID=1
$ wget --load-cookies cookies.txt \
  --content-disposition https://www.cityscapes-dataset.com/file-handling/?packageID=3
$ unzip gtFine_trainvaltest.zip && rm gtFine_trainvaltest.zip
$ rm README && rm license.txt
$ unzip leftImg8bit_trainvaltest.zip && rm leftImg8bit_trainvaltest.zip
$ rm README && rm license.txt

# Convert Cityscapes Dataset to TFRecords format.
$ cd ..
$ sed -i -e "s/python/python3/g" convert_cityscapes.sh
$ export PYTHONPATH=${HOME}/git/deeplab/models/research/deeplab/datasets/cityscapes:${PYTHONPATH}
$ sh convert_cityscapes.sh

# Create a checkpoint storage folder for training. If training is not required,
# there is no need to carry out.
$ cd ../..
$ mkdir -p deeplab/datasets/cityscapes/exp/train_on_train_set/train && \
  mkdir -p deeplab/datasets/cityscapes/exp/train_on_train_set/eval && \
  mkdir -p deeplab/datasets/cityscapes/exp/train_on_train_set/vis

# Download the DeepLabV3 trained model of the MobileNetV3 backbone.
$ curl -sc /tmp/cookie \
  "https://drive.google.com/uc?export=download&id=1f5ccaJmJBYwBmHvRQ77yGIUcXnqQIRY_" > /dev/null
$ CODE="$(awk '/_warning_/ {print $NF}' /tmp/cookie)"
$ curl -Lb /tmp/cookie \
  "https://drive.google.com/uc?export=download&confirm=${CODE}&id=1f5ccaJmJBYwBmHvRQ77yGIUcXnqQIRY_" \
  -o deeplab_mnv3_small_cityscapes_trainfine_2019_11_15.tar.gz
$ tar -zxvf deeplab_mnv3_small_cityscapes_trainfine_2019_11_15.tar.gz
$ rm deeplab_mnv3_small_cityscapes_trainfine_2019_11_15.tar.gz

$ curl -sc /tmp/cookie \
  "https://drive.google.com/uc?export=download&id=1QxS3G55rUQvuiBF-hztQv5zCkfPfwlVU" > /dev/null
$ CODE="$(awk '/_warning_/ {print $NF}' /tmp/cookie)"
$ curl -Lb /tmp/cookie \
  "https://drive.google.com/uc?export=download&confirm=${CODE}&id=1QxS3G55rUQvuiBF-hztQv5zCkfPfwlVU" \
  -o deeplab_mnv3_large_cityscapes_trainfine_2019_11_15.tar.gz
$ tar -zxvf deeplab_mnv3_large_cityscapes_trainfine_2019_11_15.tar.gz
$ rm deeplab_mnv3_large_cityscapes_trainfine_2019_11_15.tar.gz

$ export PATH_TO_INITIAL_CHECKPOINT=${HOME}/git/deeplab/models/research/deeplab_mnv3_small_cityscapes_trainfine/model.ckpt
$ export PATH_TO_DATASET=${HOME}/git/deeplab/models/research/deeplab/datasets/cityscapes/tfrecord
$ export PYTHONPATH=${HOME}/git/deeplab/models/research:${HOME}/git/deeplab/models/research/deeplab:${HOME}/git/deeplab/models/research/slim:${PYTHONPATH}

# Fix a bug in the data generator.
$ sed -i -e \
  "s/splits_to_sizes={'train_fine': 2975,/splits_to_sizes={'train': 2975,/g" \
  deeplab/datasets/data_generator.py

# Back up the trained model.
$ cd ${HOME}/git/deeplab/models/research
$ cp deeplab/export_model.py deeplab/export_model.py_org
$ cp deeplab_mnv3_small_cityscapes_trainfine/frozen_inference_graph.pb \
  deeplab_mnv3_small_cityscapes_trainfine/frozen_inference_graph_org.pb
$ cp deeplab_mnv3_large_cityscapes_trainfine/frozen_inference_graph.pb \
  deeplab_mnv3_large_cityscapes_trainfine/frozen_inference_graph_org.pb

# Customize "export_model.py" according to the input resolution. Must be (multiple of 8 + 1).
#   (example.1) 769 = 8 * 96 + 1
#   (example.2) 512 = 8 * 64 + 1
#   (example.3) 320 = 8 * 40 + 1
# And it is necessary to change from tf.uint8 type to tf.float32 type.
$ sed -i -e \
  "s/tf.placeholder(tf.uint8, \[1, None, None, 3\], name=_INPUT_NAME)/tf.placeholder(tf.float32, \[1, 769, 769, 3\], name=_INPUT_NAME)/g" \
  deeplab/export_model.py

2-2-2. Parameter sheet

# crop_size and image_pooling_crop_size are multiples of --decoder_output_stride + 1
# 769 = 8 * 96 + 1
# 513 = 8 * 64 + 1
# 321 = 8 * 40 + 1

# --initialize_last_layer=True initializes the final layer with the weight of
# tf_initial_checkpoint (inherits the weight)

# Named tuple to describe the dataset properties.
# deeplab/datasets/data_generator.py
DatasetDescriptor = collections.namedtuple(
    'DatasetDescriptor',
    [
        'splits_to_sizes',  # Splits of the dataset into training, val and test.
        'num_classes',  # Number of semantic classes, including the
                        # background class (if exists). For example, there
                        # are 20 foreground classes + 1 background class in
                        # the PASCAL VOC 2012 dataset. Thus, we set
                        # num_classes=21.
        'ignore_label',  # Ignore label value.
    ])

_CITYSCAPES_INFORMATION = DatasetDescriptor(
    splits_to_sizes={'train': 2975,
                     'train_coarse': 22973,
                     'trainval_fine': 3475,
                     'trainval_coarse': 23473,
                     'val_fine': 500,
                     'test_fine': 1525},
    num_classes=19,
    ignore_label=255,
)

_PASCAL_VOC_SEG_INFORMATION = DatasetDescriptor(
    splits_to_sizes={
        'train': 1464,
        'train_aug': 10582,
        'trainval': 2913,
        'val': 1449,
    },
    num_classes=21,
    ignore_label=255,
)

_ADE20K_INFORMATION = DatasetDescriptor(
    splits_to_sizes={
        'train': 20210,  # num of samples in images/training
        'val': 2000,  # num of samples in images/validation
    },
    num_classes=151,
    ignore_label=0,
)

_DATASETS_INFORMATION = {
    'cityscapes': _CITYSCAPES_INFORMATION,
    'pascal_voc_seg': _PASCAL_VOC_SEG_INFORMATION,
    'ade20k': _ADE20K_INFORMATION,
}

# A map from network name to network function. model_variant.
# deeplab/core/feature_extractor.py
networks_map = {
    'mobilenet_v2': _mobilenet_v2,
    'mobilenet_v3_large_seg': mobilenet_v3_large_seg,
    'mobilenet_v3_small_seg': mobilenet_v3_small_seg,
    'resnet_v1_18': resnet_v1_beta.resnet_v1_18,
    'resnet_v1_18_beta': resnet_v1_beta.resnet_v1_18_beta,
    'resnet_v1_50': resnet_v1_beta.resnet_v1_50,
    'resnet_v1_50_beta': resnet_v1_beta.resnet_v1_50_beta,
    'resnet_v1_101': resnet_v1_beta.resnet_v1_101,
    'resnet_v1_101_beta': resnet_v1_beta.resnet_v1_101_beta,
    'xception_41': xception.xception_41,
    'xception_65': xception.xception_65,
    'xception_71': xception.xception_71,
    'nas_pnasnet': nas_network.pnasnet,
    'nas_hnasnet': nas_network.hnasnet,
}

2-2-3. "mobilenet_v3_small_seg" Export Model

Generate Freeze Graph (.pb) with INPUT Placeholder changed from checkpoint file (.ckpt).

$ python3 deeplab/export_model.py \
    --checkpoint_path=./deeplab_mnv3_small_cityscapes_trainfine/model.ckpt \
    --export_path=./deeplab_mnv3_small_cityscapes_trainfine/frozen_inference_graph.pb \
    --num_classes=19 \
    --crop_size=769 \
    --crop_size=769 \
    --model_variant="mobilenet_v3_small_seg" \
    --image_pooling_crop_size="769,769" \
    --image_pooling_stride=4,5 \
    --aspp_convs_filters=128 \
    --aspp_with_concat_projection=0 \
    --aspp_with_squeeze_and_excitation=1 \
    --decoder_use_sum_merge=1 \
    --decoder_filters=19 \
    --decoder_output_is_logits=1 \
    --image_se_uses_qsigmoid=1 \
    --image_pyramid=1 \
    --decoder_output_stride=8

2-2-4. "mobilenet_v3_large_seg" Export Model

Generate Freeze Graph (.pb) with INPUT Placeholder changed from checkpoint file (.ckpt).

$ python3 deeplab/export_model.py \
    --checkpoint_path=./deeplab_mnv3_large_cityscapes_trainfine/model.ckpt \
    --export_path=./deeplab_mnv3_large_cityscapes_trainfine/frozen_inference_graph.pb \
    --num_classes=19 \
    --crop_size=769 \
    --crop_size=769 \
    --model_variant="mobilenet_v3_large_seg" \
    --image_pooling_crop_size="769,769" \
    --image_pooling_stride=4,5 \
    --aspp_convs_filters=128 \
    --aspp_with_concat_projection=0 \
    --aspp_with_squeeze_and_excitation=1 \
    --decoder_use_sum_merge=1 \
    --decoder_filters=19 \
    --decoder_output_is_logits=1 \
    --image_se_uses_qsigmoid=1 \
    --image_pyramid=1 \
    --decoder_output_stride=8

If you follow the Google Colaboratory sample procedure, copy the "deeplab_mnv3_small_cityscapes_trainfine" folder and "deeplab_mnv3_large_cityscapes_trainfine" to your Google Drive "My Drive". It is not necessary if all procedures described in Google Colaboratory are performed in a PC environment. 001 002

2-2-5. Google Colaboratory - Post-training quantization - post_training_integer_quant.ipynb

Weight Quantization
Integer Quantization
Full Integer Quantization

https://colab.research.google.com/drive/1TtCJ-uMNTArpZxrf5DCNbZdn08DsiW8F 　　

2-3. MobileNetV3+DeeplabV3+Cityscaps - Quantization-aware training

2-3-1. "mobilenet_v3_small_seg" Quantization-aware training

$ cd ${HOME}/git/deeplab/models/research
$ export PATH_TO_TRAINED_FLOAT_MODEL=${HOME}/git/deeplab/models/research/deeplab_mnv3_small_cityscapes_trainfine/model.ckpt
$ export PATH_TO_TRAIN_DIR=${HOME}/git/deeplab/models/research/deeplab/datasets/cityscapes/exp/train_on_train_set/train
$ export PATH_TO_DATASET=${HOME}/git/deeplab/models/research/deeplab/datasets/cityscapes/tfrecord

# deeplab_mnv3_small_cityscapes_trainfine
$ python3 deeplab/train.py \
    --logtostderr \
    --training_number_of_steps=5000 \
    --train_split="train" \
    --model_variant="mobilenet_v3_small_seg" \
    --train_crop_size="769,769" \
    --train_batch_size=8 \
    --dataset="cityscapes" \
    --initialize_last_layer=False \
    --base_learning_rate=3e-5 \
    --quantize_delay_step=0 \
    --image_pooling_crop_size="769,769" \
    --image_pooling_stride=4,5 \
    --aspp_convs_filters=128 \
    --aspp_with_concat_projection=0 \
    --aspp_with_squeeze_and_excitation=1 \
    --decoder_use_sum_merge=1 \
    --decoder_filters=19 \
    --decoder_output_is_logits=1 \
    --image_se_uses_qsigmoid=1 \
    --image_pyramid=1 \
    --decoder_output_stride=8 \
    --save_interval_secs=300 \
    --save_summaries_secs=300 \
    --save_summaries_images=True \
    --log_steps=100 \
    --tf_initial_checkpoint=${PATH_TO_TRAINED_FLOAT_MODEL} \
    --train_logdir=${PATH_TO_TRAIN_DIR} \
    --dataset_dir=${PATH_TO_DATASET}

2-3-2. "mobilenet_v3_large_seg" Quantization-aware training

$ cd ${HOME}/git/deeplab/models/research
$ export PATH_TO_TRAINED_FLOAT_MODEL=${HOME}/git/deeplab/models/research/deeplab_mnv3_large_cityscapes_trainfine/model.ckpt
$ export PATH_TO_TRAIN_DIR=${HOME}/git/deeplab/models/research/deeplab/datasets/cityscapes/exp/train_on_train_set/train
$ export PATH_TO_DATASET=${HOME}/git/deeplab/models/research/deeplab/datasets/cityscapes/tfrecord

# deeplab_mnv3_large_cityscapes_trainfine
$ python3 deeplab/train.py \
    --logtostderr \
    --training_number_of_steps=4350 \
    --train_split="train" \
    --model_variant="mobilenet_v3_large_seg" \
    --train_crop_size="769,769" \
    --train_batch_size=8 \
    --dataset="cityscapes" \
    --initialize_last_layer=False \
    --base_learning_rate=3e-5 \
    --quantize_delay_step=0 \
    --image_pooling_crop_size="769,769" \
    --image_pooling_stride=4,5 \
    --aspp_convs_filters=128 \
    --aspp_with_concat_projection=0 \
    --aspp_with_squeeze_and_excitation=1 \
    --decoder_use_sum_merge=1 \
    --decoder_filters=19 \
    --decoder_output_is_logits=1 \
    --image_se_uses_qsigmoid=1 \
    --image_pyramid=1 \
    --decoder_output_stride=8 \
    --save_interval_secs=300 \
    --save_summaries_secs=300 \
    --save_summaries_images=True \
    --log_steps=100 \
    --tf_initial_checkpoint=${PATH_TO_TRAINED_FLOAT_MODEL} \
    --train_logdir=${PATH_TO_TRAIN_DIR} \
    --dataset_dir=${PATH_TO_DATASET}

The orange line is "deeplab_mnv3_small_cityscapes_trainfine" loss. The blue line is "deeplab_mnv3_large_cityscapes_trainfine" loss. 003 　　

2-4. MobileNetV2+DeeplabV3+coco/voc - Post-training quantization

2-4-1. Preparation

$ cd ${HOME}/git/deeplab/models/research

$ wget http://download.tensorflow.org/models/deeplabv3_mnv2_dm05_pascal_trainaug_2018_10_01.tar.gz
$ tar -zxvf deeplabv3_mnv2_dm05_pascal_trainaug_2018_10_01.tar.gz
$ rm deeplabv3_mnv2_dm05_pascal_trainaug_2018_10_01.tar.gz

$ wget http://download.tensorflow.org/models/deeplabv3_mnv2_dm05_pascal_trainval_2018_10_01.tar.gz
$ tar -zxvf deeplabv3_mnv2_dm05_pascal_trainval_2018_10_01.tar.gz
$ rm deeplabv3_mnv2_dm05_pascal_trainval_2018_10_01.tar.gz

$ wget http://download.tensorflow.org/models/deeplabv3_mnv2_pascal_train_aug_2018_01_29.tar.gz
$ tar -zxvf deeplabv3_mnv2_pascal_train_aug_2018_01_29.tar.gz
$ rm deeplabv3_mnv2_pascal_train_aug_2018_01_29.tar.gz

$ sed -i -e \
  "s/tf.placeholder(tf.uint8, \[1, None, None, 3\], name=_INPUT_NAME)/tf.placeholder(tf.float32, \[1, 257, 257, 3\], name=_INPUT_NAME)/g" \
  deeplab/export_model.py

$ export PYTHONPATH=${HOME}/git/deeplab/models/research:${HOME}/git/deeplab/models/research/deeplab:${HOME}/git/deeplab/models/research/slim:${PYTHONPATH}

$ python3 deeplab/export_model.py \
  --checkpoint_path=./deeplabv3_mnv2_dm05_pascal_trainaug/model.ckpt \
  --export_path=./deeplabv3_mnv2_dm05_pascal_trainaug/frozen_inference_graph.pb \
  --model_variant="mobilenet_v2" \
  --crop_size=257 \
  --crop_size=257 \
  --depth_multiplier=0.5

$ python3 deeplab/export_model.py \
  --checkpoint_path=./deeplabv3_mnv2_dm05_pascal_trainval/model.ckpt \
  --export_path=./deeplabv3_mnv2_dm05_pascal_trainval/frozen_inference_graph.pb \
  --model_variant="mobilenet_v2" \
  --crop_size=257 \
  --crop_size=257 \
  --depth_multiplier=0.5

$ python3 deeplab/export_model.py \
  --checkpoint_path=./deeplabv3_mnv2_pascal_train_aug/model.ckpt-30000 \
  --export_path=./deeplabv3_mnv2_pascal_train_aug/frozen_inference_graph.pb \
  --model_variant="mobilenet_v2" \
  --crop_size=257 \
  --crop_size=257

2-5. MobileNetV3-SSD+coco - Post-training quantization

2-5-1. Preparation

$ cd ~
$ sudo pip3 install tensorflow-gpu==1.15.0
$ git clone --depth 1 https://github.com/tensorflow/models.git
$ cd models/research

$ git clone https://github.com/cocodataset/cocoapi.git
$ cd cocoapi/PythonAPI
$ make
$ cp -r pycocotools ../..
$ cd ../..
$ wget -O protobuf.zip https://github.com/google/protobuf/releases/download/v3.0.0/protoc-3.0.0-linux-x86_64.zip
$ unzip protobuf.zip
$ ./bin/protoc object_detection/protos/*.proto --python_out=.

$ sudo apt-get install -y protobuf-compiler python3-pil python3-lxml python3-tk
$ sudo -H pip3 install Cython contextlib2 jupyter matplotlib

$ export PYTHONPATH=${PWD}:${PWD}/object_detection:${PWD}/slim:${PYTHONPATH}

$ mkdir -p ssd_mobilenet_v3_small_coco_2019_08_14 && cd ssd_mobilenet_v3_small_coco_2019_08_14
$ curl -sc /tmp/cookie "https://drive.google.com/uc?export=download&id=1uqaC0Y-yRtzkpu1EuZ3BzOyh9-i_3Qgi" > /dev/null
$ CODE="$(awk '/_warning_/ {print $NF}' /tmp/cookie)"
$ curl -Lb /tmp/cookie "https://drive.google.com/uc?export=download&confirm=${CODE}&id=1uqaC0Y-yRtzkpu1EuZ3BzOyh9-i_3Qgi" -o ssd_mobilenet_v3_small_coco_2019_08_14.tar.gz
$ tar -zxvf ssd_mobilenet_v3_small_coco_2019_08_14.tar.gz
$ rm ssd_mobilenet_v3_small_coco_2019_08_14.tar.gz
$ cd ..

$ mkdir -p ssd_mobilenet_v3_large_coco_2019_08_14 && cd ssd_mobilenet_v3_large_coco_2019_08_14
$ curl -sc /tmp/cookie "https://drive.google.com/uc?export=download&id=1NGLjKRWDQZ_kibQHlLZ7Eetuuz1waC7X" > /dev/null
$ CODE="$(awk '/_warning_/ {print $NF}' /tmp/cookie)"
$ curl -Lb /tmp/cookie "https://drive.google.com/uc?export=download&confirm=${CODE}&id=1NGLjKRWDQZ_kibQHlLZ7Eetuuz1waC7X" -o ssd_mobilenet_v3_large_coco_2019_08_14.tar.gz
$ tar -zxvf ssd_mobilenet_v3_large_coco_2019_08_14.tar.gz
$ rm ssd_mobilenet_v3_large_coco_2019_08_14.tar.gz
$ cd ..

2-5-2. Create a conversion script from checkpoint format to saved_model format

import tensorflow as tf
import os
import shutil
from tensorflow.python.saved_model import tag_constants
from tensorflow.python.tools import freeze_graph
from tensorflow.python import ops
from tensorflow.tools.graph_transforms import TransformGraph

def freeze_model(saved_model_dir, output_node_names, output_filename):
  output_graph_filename = os.path.join(saved_model_dir, output_filename)
  initializer_nodes = ''
  freeze_graph.freeze_graph(
      input_saved_model_dir=saved_model_dir,
      output_graph=output_graph_filename,
      saved_model_tags = tag_constants.SERVING,
      output_node_names=output_node_names,
      initializer_nodes=initializer_nodes,
      input_graph=None,
      input_saver=False,
      input_binary=False,
      input_checkpoint=None,
      restore_op_name=None,
      filename_tensor_name=None,
      clear_devices=True,
      input_meta_graph=False,
  )

def get_graph_def_from_file(graph_filepath):
  tf.reset_default_graph()
  with ops.Graph().as_default():
    with tf.gfile.GFile(graph_filepath, 'rb') as f:
      graph_def = tf.GraphDef()
      graph_def.ParseFromString(f.read())
      return graph_def

def optimize_graph(model_dir, graph_filename, transforms, input_name, output_names, outname='optimized_model.pb'):
  input_names = [input_name] # change this as per how you have saved the model
  graph_def = get_graph_def_from_file(os.path.join(model_dir, graph_filename))
  optimized_graph_def = TransformGraph(
      graph_def,
      input_names,
      output_names,
      transforms)
  tf.train.write_graph(optimized_graph_def,
                      logdir=model_dir,
                      as_text=False,
                      name=outname)
  print('Graph optimized!')

def convert_graph_def_to_saved_model(export_dir, graph_filepath, input_name, outputs):
  graph_def = get_graph_def_from_file(graph_filepath)
  with tf.Session(graph=tf.Graph()) as session:
    tf.import_graph_def(graph_def, name='')
    tf.compat.v1.saved_model.simple_save(
        session,
        export_dir,# change input_image to node.name if you know the name
        inputs={input_name: session.graph.get_tensor_by_name('{}:0'.format(node.name))
            for node in graph_def.node if node.op=='Placeholder'},
        outputs={t.rstrip(":0"):session.graph.get_tensor_by_name(t) for t in outputs}
    )
    print('Optimized graph converted to SavedModel!')

tf.compat.v1.enable_eager_execution()

# Look up the name of the placeholder for the input node
graph_def=get_graph_def_from_file('./ssd_mobilenet_v3_small_coco_2019_08_14/frozen_inference_graph.pb')
input_name_small=""
for node in graph_def.node:
    if node.op=='Placeholder':
        print("##### ssd_mobilenet_v3_small_coco_2019_08_14 - Input Node Name #####", node.name) # this will be the input node
        input_name_small=node.name

# Look up the name of the placeholder for the input node
graph_def=get_graph_def_from_file('./ssd_mobilenet_v3_large_coco_2019_08_14/frozen_inference_graph.pb')
input_name_large=""
for node in graph_def.node:
    if node.op=='Placeholder':
        print("##### ssd_mobilenet_v3_large_coco_2019_08_14 - Input Node Name #####", node.name) # this will be the input node
        input_name_large=node.name

# ssd_mobilenet_v3 output names
output_node_names = ['raw_outputs/class_predictions','raw_outputs/box_encodings']
outputs = ['raw_outputs/class_predictions:0','raw_outputs/box_encodings:0']

# Optimizing the graph via TensorFlow library
transforms = []
optimize_graph('./ssd_mobilenet_v3_small_coco_2019_08_14', 'frozen_inference_graph.pb', transforms, input_name_small, output_node_names, outname='optimized_model_small.pb')
optimize_graph('./ssd_mobilenet_v3_large_coco_2019_08_14', 'frozen_inference_graph.pb', transforms, input_name_large, output_node_names, outname='optimized_model_large.pb')

# convert this to a s TF Serving compatible mode - ssd_mobilenet_v3_small_coco_2019_08_14
shutil.rmtree('./ssd_mobilenet_v3_small_coco_2019_08_14/0', ignore_errors=True)
convert_graph_def_to_saved_model('./ssd_mobilenet_v3_small_coco_2019_08_14/0',
                                 './ssd_mobilenet_v3_small_coco_2019_08_14/optimized_model_small.pb', input_name_small, outputs)

# convert this to a s TF Serving compatible mode - ssd_mobilenet_v3_large_coco_2019_08_14
shutil.rmtree('./ssd_mobilenet_v3_large_coco_2019_08_14/0', ignore_errors=True)
convert_graph_def_to_saved_model('./ssd_mobilenet_v3_large_coco_2019_08_14/0',
                                 './ssd_mobilenet_v3_large_coco_2019_08_14/optimized_model_large.pb', input_name_large, outputs)

2-5-3. Confirm the structure of saved_model 【ssd_mobilenet_v3_small_coco_2019_08_14】

$ saved_model_cli show --dir ./ssd_mobilenet_v3_small_coco_2019_08_14/0 --all

MetaGraphDef with tag-set: 'serve' contains the following SignatureDefs:

signature_def['serving_default']:
  The given SavedModel SignatureDef contains the following input(s):
    inputs['normalized_input_image_tensor'] tensor_info:
        dtype: DT_FLOAT
        shape: (1, 320, 320, 3)
        name: normalized_input_image_tensor:0
  The given SavedModel SignatureDef contains the following output(s):
    outputs['raw_outputs/box_encodings'] tensor_info:
        dtype: DT_FLOAT
        shape: (1, 2034, 4)
        name: raw_outputs/box_encodings:0
    outputs['raw_outputs/class_predictions'] tensor_info:
        dtype: DT_FLOAT
        shape: (1, 2034, 91)
        name: raw_outputs/class_predictions:0
  Method name is: tensorflow/serving/predict

2-5-4. Confirm the structure of saved_model 【ssd_mobilenet_v3_large_coco_2019_08_14】

$ saved_model_cli show --dir ./ssd_mobilenet_v3_large_coco_2019_08_14/0 --all

MetaGraphDef with tag-set: 'serve' contains the following SignatureDefs:

signature_def['serving_default']:
  The given SavedModel SignatureDef contains the following input(s):
    inputs['normalized_input_image_tensor'] tensor_info:
        dtype: DT_FLOAT
        shape: (1, 320, 320, 3)
        name: normalized_input_image_tensor:0
  The given SavedModel SignatureDef contains the following output(s):
    outputs['raw_outputs/box_encodings'] tensor_info:
        dtype: DT_FLOAT
        shape: (1, 2034, 4)
        name: raw_outputs/box_encodings:0
    outputs['raw_outputs/class_predictions'] tensor_info:
        dtype: DT_FLOAT
        shape: (1, 2034, 91)
        name: raw_outputs/class_predictions:0
  Method name is: tensorflow/serving/predict

2-5-5. Creating the destination path for the calibration test dataset 6GB

$ curl -sc /tmp/cookie "https://drive.google.com/uc?export=download&id=1Uk9F4Tc-9UgnvARIVkloSoePUynyST6E" > /dev/null
$ CODE="$(awk '/_warning_/ {print $NF}' /tmp/cookie)"
$ curl -Lb /tmp/cookie "https://drive.google.com/uc?export=download&confirm=${CODE}&id=1Uk9F4Tc-9UgnvARIVkloSoePUynyST6E" -o TFDS.tar.gz
$ tar -zxvf TFDS.tar.gz
$ rm TFDS.tar.gz

2-5-6. Quantization

2-5-6-1. ssd_mobilenet_v3_small_coco_2019_08_14

import tensorflow as tf
import tensorflow_datasets as tfds
import numpy as np

def representative_dataset_gen():
  for data in raw_test_data.take(100):
    image = data['image'].numpy()
    image = tf.image.resize(image, (320, 320))
    image = image[np.newaxis,:,:,:]
    yield [image]

tf.compat.v1.enable_eager_execution()

# Generating a calibration data set
#raw_test_data, info = tfds.load(name="coco/2017", with_info=True, split="test", data_dir="./TFDS")
raw_test_data, info = tfds.load(name="coco/2017", with_info=True, split="test", data_dir="./TFDS", download=False)
print(info)

# Weight Quantization - Input/Output=float32
converter = tf.lite.TFLiteConverter.from_saved_model('./ssd_mobilenet_v3_small_coco_2019_08_14/0')
converter.optimizations = [tf.lite.Optimize.OPTIMIZE_FOR_SIZE]
tflite_quant_model = converter.convert()
with open('./ssd_mobilenet_v3_small_coco_2019_08_14/mobilenet_v3_small_weight_quant.tflite', 'wb') as w:
    w.write(tflite_quant_model)
print("Weight Quantization complete! - mobilenet_v3_small_weight_quant.tflite")

# Integer Quantization - Input/Output=float32
converter = tf.lite.TFLiteConverter.from_saved_model('./ssd_mobilenet_v3_small_coco_2019_08_14/0')
converter.optimizations = [tf.lite.Optimize.DEFAULT]
converter.representative_dataset = representative_dataset_gen
tflite_quant_model = converter.convert()
with open('./ssd_mobilenet_v3_small_coco_2019_08_14/mobilenet_v3_small_integer_quant.tflite', 'wb') as w:
    w.write(tflite_quant_model)
print("Integer Quantization complete! - mobilenet_v3_small_integer_quant.tflite")

# Full Integer Quantization - Input/Output=int8
converter = tf.lite.TFLiteConverter.from_saved_model('./ssd_mobilenet_v3_small_coco_2019_08_14/0')
converter.optimizations = [tf.lite.Optimize.DEFAULT]
converter.representative_dataset = representative_dataset_gen
converter.target_spec.supported_ops = [tf.lite.OpsSet.TFLITE_BUILTINS_INT8]
converter.inference_input_type = tf.uint8
converter.inference_output_type = tf.uint8
tflite_quant_model = converter.convert()
with open('./ssd_mobilenet_v3_small_coco_2019_08_14/mobilenet_v3_small_full_integer_quant.tflite', 'wb') as w:
    w.write(tflite_quant_model)
print("Full Integer Quantization complete! - mobilenet_v3_small_full_integer_quant.tflite")

2-5-6-2. ssd_mobilenet_v3_large_coco_2019_08_14

import tensorflow as tf
import tensorflow_datasets as tfds
import numpy as np

def representative_dataset_gen():
  for data in raw_test_data.take(100):
    image = data['image'].numpy()
    image = tf.image.resize(image, (320, 320))
    image = image[np.newaxis,:,:,:]
    yield [image]

tf.compat.v1.enable_eager_execution()

# Generating a calibration data set
#raw_test_data, info = tfds.load(name="coco/2017", with_info=True, split="test", data_dir="./TFDS")
raw_test_data, info = tfds.load(name="coco/2017", with_info=True, split="test", data_dir="./TFDS", download=False)

# Weight Quantization - Input/Output=float32
converter = tf.lite.TFLiteConverter.from_saved_model('./ssd_mobilenet_v3_large_coco_2019_08_14/0')
converte